Academic year 2017/2018
- Course ID
- Teaching staff
- Matteo Ruggiero
James Edward Griffin
- 2nd year
- Teaching period
- First semester
- D.M. 270 TAF C - Related or integrative
- Course disciplinary sector (SSD)
- SECS-S/01 - statistica
- Formal authority
- Type of examination
- STOCHASTIC MODELLING FOR STATISTICAL APPLICATIONS
Sommario del corso
The course aims at providing a modern overview of Bayesian statistical methods, covering the fundamentals of both the parametric and the nonparametric approach. The course will focus on the key probabilistic concepts, stochastic modelling tools and most widely used computational strategies at the basis of the most recent advances in the field.
A short module of the course will be taught by Visiting Professor Jim Griffin on Computational methods for Bayesian nonparametrics (see International visiting professors).
Results of learning outcomes
Students will learn how to model statistical problems with Bayesian parametric and nonparametric tools, study the theoretical properties of the involved objects and devise appropriate computational algorithms for their implementation.
The course consists of roughly 80% of class lectures, and 20% of computer lab sessions.
Learning assessment methods
The exam consists in the oral verification of the material covered in class on the parametric and the nonparametric module. The final mark will be the average of the two evaluations given by the two lecturers on their respective parts.
In addition to the above, students can optionally present and discuss a scientific paper (e.g., one of those referenced during the course) with the aid of a slide presentation (in which case they should bring their own personal device to the exam). The students are encouraged to agree upon the paper to be presented with the teacher whose module is more relevant for the topic. In this case, the examination on such module will be shorter.
- Motivation and foundations of Bayesian inference: exchangeability and de Finetti's representation theorems
- Conjugacy, posteriors and parametric families of conjugate models
- Markov chain Monte Carlo methods for parametric inference
- The Bayesian nonparametric framework
- The Dirichlet process: definition and properties
- Constructions of the Dirichlet process
- Hierarchical priors derived from the Dirichlet process
- Prior models beyond the Dirichlet process
- Markov chain Monte Carlo methods for nonparametric inference
Suggested readings and bibliography
Lecture notes will be made available. Additional suggested reading are:
HOFF, P.D. (2009). A First Course in Bayesian Statistical Methods. Springer.
GHOSAL, S. and VAN DER VAART, A. (2017). Theory of nonparametric Bayesian inference. Cambridge University Press.
HJORT, N., HOLMES, C., MUELLER, P. and WALKER, S.G. (eds.) (2010). Bayesian Nonparametrics. Cambridge University Press.
GHOSH, J.K. and RAMAMOORTHI, R.V. (2003). Bayesian Nonparametrics. Springer.
This course will be delivered at the ESOMAS Department.